paper-with-me

Papers

On the Efficient Implementation of High Accuracy Optimality of Profile Maximum Likelihood

2022-10-13 · Moses Charikar, Zhihao Jiang, Kirankumar Shiragur, Aaron Sidford

We provide an efficient unified plug-in approach for estimating symmetric properties of distributions given $n$ independent samples. Our estimator is based on profile-maximum-likelihood (PML) and is sample optimal for estimating various symmetric properties when the estimation error $\epsilon \gg n^{-1/3}$. This result improves upon the previous best accuracy threshold of $\epsilon \gg n^{-1/4}$ achievable by polynomial time computable PML-based universal estimators [ACSS21, ACSS20]. Our estimator reaches a theoretical limit for universal symmetric property estimation as [Han21] shows that a broad class of universal estimators (containing many well known approaches including ours) cannot be sample optimal for every $1$-Lipschitz property when $\epsilon \ll n^{-1/3}$.

📄 PDF Abstract BibTeX arXiv:2210.06728

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Explicit Time-Optimal Speed Profiles for Planar Paths with Monotone Curvature

2022-08-25 · Daniel Selvaratnam, Michael Cantoni, Chris Manzie

Minimum-time speed profiles are constructed for planar paths with smooth strictly-monotonic signed curvature, subject to constraints on velocity, normal acceleration and tangential acceleration. The construction is expli…

Instance Based Approximations to Profile Maximum Likelihood

2020-11-05 · NeurIPS 2020 12 · Nima Anari, Moses Charikar, Kirankumar Shiragur, Aaron Sidford

In this paper we provide a new efficient algorithm for approximately computing the profile maximum likelihood (PML) distribution, a prominent quantity in symmetric property estimation. We provide an algorithm which match…

The Broad Optimality of Profile Maximum Likelihood

2019-06-10 · NeurIPS 2019 12 · Yi Hao, Alon Orlitsky

We study three fundamental statistical-learning problems: distribution estimation, property estimation, and property testing. We establish the profile maximum likelihood (PML) estimator as the first unified sample-optima…

Inverse Reinforcement Learning via Matching of Optimality Profiles

2020-11-18 · Luis Haug, Ivan Ovinnikov, Eugene Bykovets

The goal of inverse reinforcement learning (IRL) is to infer a reward function that explains the behavior of an agent performing a task. The assumption that most approaches make is that the demonstrated behavior is near-…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Optimized Decoding-Energy-Aware Encoding in Practical VVC Implementations

2022-06-27 · Matthias Kränzler, Adam Wieckowski, Geetha Ramasubbu, Benjamin Bross 외

The optimization of the energy demand is crucial for modern video codecs. Previous studies show that the energy demand of VVC decoders can be improved by more than 50% if specific coding tools are disabled in the encoder…